Panoramic Image
Panoramic images, encompassing a 360° field of view, are increasingly important in computer vision, offering a comprehensive view of the surrounding environment. Current research focuses on improving semantic segmentation, 3D scene generation, and video creation from panoramic data, often employing diffusion models, transformers, and neural radiance fields to address challenges like distortion, data scarcity, and computational cost. These advancements have significant implications for applications such as autonomous driving, virtual and augmented reality, and robotics, enabling more robust and immersive experiences.
Papers
Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting
Hao Ai, Zidong Cao, Haonan Lu, Chen Chen, Jian Ma, Pengyuan Zhou, Tae-Kyun Kim, Pan Hui, Lin Wang
360ORB-SLAM: A Visual SLAM System for Panoramic Images with Depth Completion Network
Yichen Chen, Yiqi Pan, Ruyu Liu, Haoyu Zhang, Guodao Zhang, Bo Sun, Jianhua Zhang